Your audits, in your terminal.

One command for real growth context.

Install nothing globally. Authenticate once, and every audit and recording on your account is a command away, in a format your coding agent can read.

# authenticate to your Mimetic account (opens the browser, device-code flow)
npx -y --package @mimeticinc/mim-cli mim auth login

# now pull context for one of your projects
mim context --project yourstore.com

Credentials are stored in ~/.mim/config.json (chmod 600) and scoped to the projects your account owns. Requires Node 20+.

• mim projectsList the sites/projects on your account.
• mim contextPrint a growth-context pack for a project, ready to paste into Claude Code or Codex.
• mim recordingsSession-replay summaries: what each visitor did, console errors, and the likely point of friction.
• mim replay --latestOne replay's issues plus a redacted, plain-English narrative of the session.
• mim findingsThe audit's prioritized findings and backlog for a project.
• mim audit start <url> --waitRun a fresh audit and block until the report is ready.
• mim fixes listSee which findings are fixable as a pull request.
• mim fixes start <rank>Queue a code fix, Mimetic opens a PR with a preview link for you to review and merge.

Or call it directly.

Every CLI command is a JSON endpoint under /api/mim. Authenticate with the bearer token mim auth login issues, project-scoped, no scraping, no headless browser to run yourself.

# list your projects
curl https://trymimetic.com/api/mim/projects \
  -H "Authorization: Bearer mim_xxx"

# start an audit and poll for the report
curl -X POST https://trymimetic.com/api/mim/audits \
  -H "Authorization: Bearer mim_xxx" \
  -d '{"url":"https://yourstore.com","mode":"slim"}'

Tokens are scoped to the projects you own and billed per project. Session-replay recordings require the replay add-on on an active plan.

Hand it to your coding agent.

Mimetic ships a read-only MCP server, so Claude Code and Codex can see what's broken and why, redacted session narratives and findings, never raw replay payloads.

# wire Mimetic into Claude Code or Codex
mim mcp install claude
mim mcp install codex

Your agent then reads findings and replay insights on demand and can open fixes as PRs, review and merge, or close them.

Building an AI agent?

Mimetic exposes a pay-per-call audit over the x402 protocol, your agent pays in USDC on Base and gets a full report, no account or API key. It's even discoverable in the x402 bazaar.